run_select_query · Doris-MCP-Lite MCP: Risk & Policy

WHAT IT DOES

What run_select_query does on Doris-MCP-Lite

AI agents invoke run_select_query to trigger actions in Doris-MCP-Lite. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why run_select_query needs a policy

Although described as read-only SELECT queries, this tool actively executes SQL against a database. The server claims read-only enforcement, but 'run' and 'execute' semantics place this in Execute rather than Read. If the read-only constraint is bypassed or improperly enforced, arbitrary SQL could be run.

From the tool's definition 'run a read-only select query' — executes SQL queries against the database

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_select_query Rate-limited

run_select_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_select_query": {
      "limits": [
        {
          "counter": "run_select_query_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Doris-MCP-Lite, so you can run agents against it safely.

FAQ

Questions about run_select_query

What does the run_select_query tool do? +

run a read-only select query and return formatted result. It is categorised as a Execute tool in the Doris-MCP-Lite MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_select_query? +

Register the Doris-MCP-Lite MCP server in PolicyLayer and add a rule for run_select_query: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Doris-MCP-Lite. Nothing to install.

What risk level is run_select_query? +

run_select_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_select_query? +

Yes. Add a rate_limit block to the run_select_query rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block run_select_query completely? +

Set action: deny in the PolicyLayer policy for run_select_query. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides run_select_query? +

run_select_query is provided by the Doris-MCP-Lite MCP server (nomotok/doris-mcp-lite). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.